Description
Write specifications and executable acceptance criteria that AI coding agents can build from, configure GitHub issue forms and Projects to manage them, and verify delivered work in deploy previews.
Price$1,000Per person
Time10 course hoursOn-demand video and labs, plus 1 hour of coaching
DeliveryOn-demand asynchronous trainingWith online support and 1 hour of coaching
CredentialCertificate of completionFrom We Can Code IT
Your capstone, reviewed by a coach
You finish by specifying a real feature, having an AI coding agent build it, and accepting or rejecting it on the evidence, and your coach reviews that decision with you. That review is part of earning your certificate.
Group coaching for teams
Each learner gets 1 hour of coaching. Teams pool their hours into group sessions, so a team of 6 shares 6 hours of group coaching.
About this course
When AI coding agents write the code, building gets fast and the specification becomes the limit. This course teaches product owners to write specifications an agent can build from directly: a clear problem and scope, acceptance criteria in the form "when X happens, the system does Y", and a concrete check for each criterion. You configure GitHub issue forms and a Projects board to hold that work, direct an AI coding agent to build a feature, and verify the result in a deploy preview before you accept it.
Who it is for
This course is for product owners, product managers, business analysts, and entrepreneurs and founders who define what gets built by developers and AI coding agents.
Prerequisites
Experience defining features or requirements; Introduction to GitHub with AI is helpful
Requirements
Any computer with a modern browser
A free GitHub account and access to an AI coding agent that can open pull requests, such as the GitHub Copilot coding agent (paid Copilot plan, Pro or higher) or Claude Code (paid Claude plan, Pro or higher); we confirm your access before you start
A starter repository already connected to deploy previews is provided, so no hosting setup is needed
Access to an AI assistant such as Claude or ChatGPT, following your employer's data privacy rules
What you will be able to do
- You will be able to turn a loose idea into a specification with a problem statement, scope, non-goals and acceptance criteria written as "when X happens, the system does Y".
- You will be able to attach a concrete, runnable check to every acceptance criterion so anyone can verify it.
- You will be able to configure GitHub issue forms and a Projects board with custom fields, owners and automated status for a two-sprint ready queue.
- You will be able to direct an AI coding agent to build a feature from your specification and verify the result in a deploy preview.
- You will be able to accept or reject delivered work against its acceptance checks and keep a record of what is shipped, planned or cut, backed by evidence.
Syllabus
1
Why AI moved the bottleneck to the specification 1 hour
Agents build fast from clear input, Where vague specs fail, Measuring your own ready queue, Owners on every item.
Lab: You will measure a sample board: how much work is ready to build and how much has no owner or no checks.
2
Shaping an idea into a specification 1.5 hours
Problem, users and outcome, Scope and non-goals, Using an AI assistant to interview you, Cutting to a first version.
Lab: You will shape a loose idea into a one-page specification with an AI assistant.
3
Acceptance criteria with runnable checks 2 hours
"When X, the system does Y", One check per criterion, Checks that can fail, Writing checks before the build.
Lab: You will write five acceptance criteria with checks, then run them against a provided, deliberately wrong build to see which ones catch it.
4
GitHub issue forms and Projects 1.5 hours
Issue forms for specifications, Projects custom fields and views, Status automations, Dates and owners on cards.
Lab: You will configure an issue form and a Projects board holding two sprints of ready work.
5
Directing an AI coding agent 1.5 hours
Assigning an issue to an agent, Draft pull requests, Deploy previews, Reading what changed.
Lab: You will assign your specification to an AI coding agent and follow its pull request to a deploy preview.
6
Accepting work against evidence 1 hour
Verifying in a deploy preview, Accepting or rejecting against the spec, Closed is not shipped, A record of shipped, planned and cut.
Lab: You will verify three delivered changes against their checks, accept or reject each in writing, and audit a board against the live app.
7
Capstone 1.5 hours
Specification, Acceptance checks, Ready queue, Agent build, Acceptance decision.
Lab: You will specify a real feature, have an AI coding agent build it, and accept or reject it with your coach.
+
Coaching sessions 1 hour
Your coach reviews your capstone with you and answers questions as you work. Teams pool their hours into group sessions, so a team of 6 shares 6 hours of group coaching.
How it is delivered
How you learn
On-demand asynchronous training with online support, plus 1 hour of coaching.
Live or in person
Live online or in-person sessions are available for an additional fee. Email admissions@wecancodeit.org for details.
Frequently asked questions
What is spec-driven development in simple terms?
You write down what the software must do, and how to check it, before anyone or any AI writes code. The AI builds from that specification, and the checks show whether it worked.
How do I write specs for AI coding agents?
State the problem, the scope and what is out of scope, then write each requirement as "when X happens, the system does Y" with a check that can pass or fail. This course practices that on real features.
What is the product owner's role when AI writes the code?
The product owner keeps well-specified work ready, defines how each piece will be checked, and accepts or rejects delivered work against those checks.
Is spec-driven development the opposite of agile?
No. It fits inside agile teams. It changes what a ready item looks like: every item carries acceptance criteria with checks an AI agent and a reviewer can both use.
What does the coaching include?
Each learner gets 1 hour of coaching. Your coach reviews your capstone with you and answers questions as you work through the labs. Teams pool their hours into group sessions, so a team of 6 shares 6 hours of group coaching.
How long does it take and what does it cost?
10 course hours of on-demand video and labs plus 1 hour of coaching, for $1,000 per person. Access to a paid AI coding agent, such as Copilot Pro or Claude Pro, is extra.
Related courses
Build software with Claude Code from written plans: configure CLAUDE.md and agent settings, write verify-first acceptance checks, build in small tested pull requests, review with a second AI model and add security checks to CI.
10 course hours, $1,000
Build software with OpenAI Codex from written plans: configure AGENTS.md and agent settings, write verify-first acceptance checks, build in small tested pull requests, review with a second AI model and add security checks to CI.
10 course hours, $1,000
Set up a shared delivery system for a product owner and engineer working with AI coding agents: a working agreement, a weekly cycle, two approval gates in GitHub, and evidence-based reviews.
8 course hours, $800
Enroll your team
One or a few learners
Choose the number of seats, add the course to your cart and check out.
A group, or a written quote
Send the form below for group enrollment or a written quote. We reply within one business day. You can also email admissions@wecancodeit.org.
We Can Code IT, LLC, 26300 Cedar Rd, Suite 1105, Beachwood, OH 44122. Registered with the Ohio State Board of Career Colleges and Schools, Registration No. 15-03-2064T.
